Posted by admin

Claude Code told me to come back in five hours, even though almost none of my usage came from what I actually typed. The real problem was hidden inside context, cache resets, tool output, MCP servers, subagents, and scheduled tasks. In this video, I break down how Claude Code token consumption actually works, show the mistakes quietly burning through your limits, and give you a prompt that audits your own setup. What’s covered: 0:00 Why Claude Code runs out of tokens 0:58 How context compounds on every message 1:52 Audit your Claude Code token usage 2:47 Fix 1: Clear between different jobs 4:32 Fix 2: Stop switching models mid-session 6:20 Fix 3: Filter massive tool output 7:39 Fix 4: Disable unused MCP servers 10:17 When subagents save tokens and when they waste them 12:28 Pick the right model before starting 12:55 The scheduled-task trap burning tokens overnight 14:39 Token-saving advice that does not work 16:24 How to monitor context, usage, cost, and burn rate 18:10 The complete token-saving system 19:03 Run the audit regularly --- Paste this into Claude Code: Audit this setup for token waste. Do not fix anything. Report only. Use your shell and file tools to measure each item. If you cannot invoke slash commands yourself, ask me to run /context and /usage and paste the output, then continue. 1. MEMORY Find every CLAUDE.md in scope: this project, parent directories, the user level one, and anything pulled in with @imports. Report each file's size in tokens. Flag any single file over 5k and any total over 10k. 2. TOOLS List connected MCP servers and how many tools each exposes. State plainly whether tool deferral is ACTIVE or NOT. Then check for a proxy or gateway (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, any gateway variable) and say so loudly if you find one, because routing through a proxy silently turns deferral off and nothing warns you. 3. MODEL Report the current model and effort level and where each is set. Flag any mode that changes model automatically during a session, because every switch rebuilds the whole cache. 4. HOOKS List any PreToolUse hooks that rewrite noisy commands to produce less output. If there are none, say so, because unfiltered test and build output lands in context verbatim and is re-sent for the rest of the session. 5. SUBAGENTS List every agent file in the project and user agent directories. For each, report whether it sets an explicit model in frontmatter or inherits the main session's model. 6. SCHEDULED WORK List every cron, scheduled task and background job with its interval. Compare each interval against the prompt cache lifetime. Flag every one whose interval is longer, because those miss cache on every single fire. 7. CACHE Parse the newest session log under the projects directory. For every assistant turn, sum usage.cache_read_input_tokens, cache_creation_input_tokens, input_tokens and output_tokens. Report each as a percentage of the total. Also report the context size on the first turn and on the last turn. Output one table, sorted by cost, highest first: FINDING | SEVERITY | EVIDENCE | WHAT IT IS COSTING ME Severity is RED, AMBER or GREEN. Evidence is a number or a file path, never an adjective. Then one final line: the single highest-leverage change I should make. One line, nothing else. Rules: measure, do not estimate. Write UNKNOWN rather than guessing. Change no file and no setting. --- Run the audit again whenever you add a plugin, MCP server, scheduled task, or major instruction file. Small configuration changes compound quickly. Subscribe for more practical Claude Code, AI agent, and automation workflows.